Hugging Face's logo

joseph10
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Metrics Community
joseph10 commited on
Commit
549bbd2
·
1 Parent(s): a7b6012

Training in progress, epoch 1

Browse files
Files changed (15) hide show
  1. logs/events.out.tfevents.1701751745.joseph_legion.10272.0 +2 -2
  2. logs/events.out.tfevents.1701752681.joseph_legion.10272.1 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-527/config.json +34 -0
  5. run-0/checkpoint-527/model.safetensors +3 -0
  6. run-0/checkpoint-527/optimizer.pt +3 -0
  7. run-0/checkpoint-527/rng_state.pth +3 -0
  8. run-0/checkpoint-527/scheduler.pt +3 -0
  9. run-0/checkpoint-527/special_tokens_map.json +7 -0
  10. run-0/checkpoint-527/tokenizer.json +0 -0
  11. run-0/checkpoint-527/tokenizer_config.json +57 -0
  12. run-0/checkpoint-527/trainer_state.json +39 -0
  13. run-0/checkpoint-527/training_args.bin +3 -0
  14. run-0/checkpoint-527/vocab.txt +0 -0
  15. training_args.bin +1 -1
logs/events.out.tfevents.1701751745.joseph_legion.10272.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b58c5d63f0f74a5432b79d217a0554aa8f9d3a4149afde2ad8c87bd0b82e6651
3
- size 7158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0d131c041fa1b6b0799cacd06f2f30b3d14d105499221802e7a54a56130790
3
+ size 7992
logs/events.out.tfevents.1701752681.joseph_legion.10272.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3045ad86a35de0db0e0f5a5b0e337b47ff80523e6e2da26812081990345bc8d5
3
+ size 4775
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae7d24717406b5952b6aa18d0b70dd82d59ce3cbd65a86a1cd815152c808dca7
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8045071fd7ce775807243eaa915fc60a3be554095a0cfa3cda77059577a9f73
3
  size 17549312
run-0/checkpoint-527/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8045071fd7ce775807243eaa915fc60a3be554095a0cfa3cda77059577a9f73
3
+ size 17549312
run-0/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35561130002c0dc7445a8a13b97a333917455dc63c9fbd93d3e00c301ac6b5b9
3
+ size 35123898
run-0/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404cec57a6bbb572f62bd49cfe2447e0a3410a29e1c658f2617325852b27cc2d
3
+ size 14308
run-0/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a361356c3a704e63e3ae6f13da0e9be6b5807163ce7af8e69ab5cbb9c0df9bec
3
+ size 1064
run-0/checkpoint-527/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-527/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-0/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8084862385321101,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-0\\checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 0.0006568555243553003,
14
+ "loss": 0.9823,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8084862385321101,
20
+ "eval_loss": 1.3724825382232666,
21
+ "eval_runtime": 1.7972,
22
+ "eval_samples_per_second": 485.194,
23
+ "eval_steps_per_second": 3.895,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 5270,
29
+ "num_train_epochs": 10,
30
+ "save_steps": 500,
31
+ "total_flos": 8057768762220.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.5351224538156584,
35
+ "learning_rate": 0.0007298394715058892,
36
+ "num_train_epochs": 10,
37
+ "temperature": 24
38
+ }
39
+ }
run-0/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8a46880b57d8b0b9e418b052abbb3948b438121f71f7c4ea0a153d96e30889
3
+ size 4664
run-0/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebef841f41057cfd2c17275da05bf4137fc9fb9d87a24c5f6bcb0a0491c66452
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8a46880b57d8b0b9e418b052abbb3948b438121f71f7c4ea0a153d96e30889
3
  size 4664